Philter identifies and redacts sensitive information such as PII and PHI from text and documents.

Philter can help you maintain HIPAA compliance, meet industry regulations, and leverage your documents for valuable secondary purposes.

Philter’s API allows for easy integration in your existing systems. Philter runs in your cloud. Your data never leaves your cloud and is not sent to any third-party.

FAQ | User’s Guide | Release Notes | Case Studies

De-identify ChatGPT API Requests

The Philter OpenAI Proxy removes PII and PHI from OpenAI (ChatGPT) API requests. Learn more about it in our blog post.

Philter runs in your cloud and your data stays in your cloud.

Philter’s Lenses

Philter uses trained AI models we call lenses.

Each lens is specially trained for different domains of text and can give Philter increased performance when deidentifying text in that domain.

You probably wouldn’t want to try to deidentify healthcare text using a lens created for news, for instance!

Contact us to learn how to use a custom lens or to learn more about how we train and evaluate them.

General Lenses

Our general lenses are trained on a variety of text intended to be usable across multiple domains.

The general lenses include:

  • General
  • General (lite)

Philter uses a general lens by default for broad applicability.

Specialty Lenses

Our specialty lenses are trained on specific domains to increase Philter’s performance when deidentifying text in those domains.

The specialty lenses include:

  • Healthcare (general)
  • Healthcare (COVID-19)
  • Legal (general)
  • Legal (contracts)
  • News (general)